A Large Language Model Based Method for Complex Logical Reasoning over Knowledge Graphs
This addresses the problem of handling complex first-order logic queries over incomplete knowledge graphs for AI researchers, offering a robust alternative to embedding methods, though it appears incremental as it builds on existing retrieval and LLM techniques.
The paper tackles the challenge of complex logical reasoning over knowledge graphs by proposing ROG, a framework that combines query-aware retrieval with LLM-based chain-of-thought reasoning, which outperforms embedding-based baselines on benchmarks with notable gains in mean reciprocal rank for high-complexity queries.
Reasoning over knowledge graphs (KGs) with first-order logic (FOL) queries is challenging due to the inherent incompleteness of real-world KGs and the compositional complexity of logical query structures. Most existing methods rely on embedding entities and relations into continuous geometric spaces and answer queries via differentiable set operations. While effective for simple query patterns, these approaches often struggle to generalize to complex queries involving multiple operators, deeper reasoning chains, or heterogeneous KG schemas. We propose ROG (Reasoning Over knowledge Graphs with large language models), an ensemble-style framework that combines query-aware KG neighborhood retrieval with large language model (LLM)-based chain-of-thought reasoning. ROG decomposes complex FOL queries into sequences of simpler sub-queries, retrieves compact, query-relevant subgraphs as contextual evidence, and performs step-by-step logical inference using an LLM, avoiding the need for task-specific embedding optimization. Experiments on standard KG reasoning benchmarks demonstrate that ROG consistently outperforms strong embedding-based baselines in terms of mean reciprocal rank (MRR), with particularly notable gains on high-complexity query types. These results suggest that integrating structured KG retrieval with LLM-driven logical reasoning offers a robust and effective alternative for complex KG reasoning tasks.